yfedoseev/pdf_oxide

The fastest PDF library for Python and Rust. Text extraction, image extraction, markdown conversion, PDF creation & editing. 0.8ms mean, 5× faster than industry leaders, 100% pass rate on 3,830 PDFs. MIT/Apache-2.0.

What it solves

PDFOxide is a high-performance PDF toolkit designed to solve the speed and licensing restrictions of existing PDF libraries. It provides a fast, MIT-licensed alternative to libraries like PyMuPDF, enabling efficient text, image, and layout extraction from PDFs across 20 different programming languages.

How it works

The project uses a core written in Rust for maximum performance and stability, providing a stable C ABI. This core is then wrapped in idiomatic bindings for 19 other languages (including Python, Go, JS/TS, C#, Java, and C++). It supports a wide range of functions including text extraction, markdown conversion, image extraction, and PDF editing (such as filling form fields).

Who it’s for

  • AI/LLM Developers: Those building RAG (Retrieval-Augmented Generation) pipelines that need to convert PDFs to clean Markdown for LLM consumption.
  • AI Assistants: Users of Claude, Cursor, or other MCP-compatible tools who want local PDF access via the provided MCP server.
  • Enterprise Software Engineers: Developers needing a reliable, permissively licensed toolkit for large-scale document processing.
  • Academic Researchers: Those parsing large corpora of academic papers.

Highlights

  • Extreme Speed: Benchmarked at 0.8ms mean per document, significantly faster than PyMuPDF and pypdf.
  • Broad Language Support: Native bindings for 20 languages, including Rust, Python, Go, and WASM.
  • High Reliability: 100% pass rate on a corpus of 3,830 real-world PDFs.
  • AI-Ready: Includes a dedicated MCP server for AI assistants and built-in Markdown conversion for RAG pipelines.
  • Permissive Licensing: Dual-licensed under MIT/Apache-2.0, avoiding AGPL restrictions.

Related

  • Project
    firecrawl/pdf-inspector

    A fast Rust-based library for PDF classification and text extraction that converts PDFs to structured Markdown and selectively applies OCR only when necessary.

  • Project
    run-llama/liteparse

    LiteParse is a fast, local, open-source PDF parsing tool that extracts spatial text and structure into Markdown or JSON without cloud dependencies.

  • Project
    docling-project/docling-parse

    Docling Parse is a fast, configurable PDF‑parsing library (Python API with a C++ core) that extracts text, words, lines, vector shapes and bitmap images together with their coordinates. It supports both sequential and multi‑threaded parsing, lets you choose what to compute or materialize per page, and includes rendering utilities. Ideal for AI workflows that need layout‑aware document data.

  • Project
    pymupdf/PyMuPDF

    A high-performance Python library for extracting and manipulating PDF and Office documents, featuring specialized tools for converting documents into LLM-ready Markdown for RAG pipelines.

  • Project
    firecrawl/anydoc

    anydoc is a pure‑Rust library (with Node, Python, and WebAssembly bindings) that converts 14 office‑document formats into consistent GitHub‑Flavored Markdown in a few milliseconds. It preserves document structure, supports optional hosted OCR for scanned PDFs, and is packaged as a CLI, an Agent Skill, and language‑specific SDKs, making it ideal for LLM‑oriented pipelines that need fast, uniform text extraction.